Paper: Automatically Learning Cognitive Status For Multi-Document Summarization Of Newswire

ACL ID H05-1031
Title Automatically Learning Cognitive Status For Multi-Document Summarization Of Newswire
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

Machine summaries can be improved by using knowledge about the cognitive sta- tus of news article referents. In this paper, we present an approach to automatically acquiring distinctions in cognitive status using machine learning over the forms of referring expressions appearing in the in- put. We focus on modeling references to people, both because news often revolve around people and because existing natu- ral language tools for named entity iden- ti cation are reliable. We examine two speci c distinctions whether a person in the news can be assumed to be known to a target audience (hearer-old vs hearer-new) and whether a person is a major charac- ter in the news story. We report on ma- chine learning experiments that show that these distinctions can be learned with high accuracy, and va...